Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 170 466 484 844 942 915 865 555 341 968 160 876 809 429 242 894 485 408 917 305
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 865 915 809 160 341  NA 844 485 894  NA 170 242 876  NA 466 917 968 408 305 942 429 484 555
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 2 2 1 4 2 1 5 1 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "j" "t" "s" "q" "u" "I" "L" "Z" "R" "Q"

Are all/any elements TRUE

  • Input: logical vector
  • Output: single logical value
  • Task: try, understand what happens when you use manyNumbersWithNA instead of manyNumbers.
all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  5  6 10 19
which( manyNumbersWithNA > 900 )
[1]  2 16 17 20
which( is.na( manyNumbersWithNA ) )
[1]  6 10 14

Filtering vector elements

  • Input: any vector and filtering condition
  • Output: elements of the input vector
  • Note: several ways to get the same effect
manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 942 915 968 917
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 942 915 968 917
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 942 915 968 917

Are some elements among other elements

  • Input: two vectors
  • Output: a logical vector corresponding to the first input vector
"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "I" "L" "Z" "R" "Q"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "j" "t" "s" "q" "u"
manyNumbers %in% 300:600
 [1] FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE
[18]  TRUE FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  2  3  8  9 14 17 18 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

  • Input: a logical vector and two vectors additional vectors (for TRUE, for FALSE)
  • Output: elements of the additional vectors
  • Note: it can take care of NAs
if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "large" "large" "small" "small" NA      "large" "small" "large" NA      "small" "small" "large"
[14] NA      "small" "large" "large" "small" "small" "large" "small" "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "large"   "large"   "small"   "small"   "UNKNOWN" "large"   "small"   "large"   "UNKNOWN"
[11] "small"   "small"   "large"   "UNKNOWN" "small"   "large"   "large"   "small"   "small"   "large"  
[21] "small"   "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 865 915 809   0   0  NA 844   0 894  NA   0   0 876  NA   0 917 968   0   0 942   0   0 555

Duplicates and unique elements

  • Input: a vector
unique( duplicatedNumbers )
[1] 3 2 1 4 5
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  2  1  4  5
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 17
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 968
which.min( manyNumbersWithNA )
[1] 4
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 160
range( manyNumbersWithNA, na.rm = TRUE )
[1] 160 968

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 865 915 809 160 341  NA 844 485 894  NA 170 242 876  NA 466 917 968 408 305 942 429 484 555
sort( manyNumbersWithNA )
 [1] 160 170 242 305 341 408 429 466 484 485 555 809 844 865 876 894 915 917 942 968
sort( manyNumbersWithNA, na.last = TRUE )
 [1] 160 170 242 305 341 408 429 466 484 485 555 809 844 865 876 894 915 917 942 968  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 968 942 917 915 894 876 865 844 809 555 485 484 466 429 408 341 305 242 170 160  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 865 915 809 160 341
order( manyNumbersWithNA[1:5] )
[1] 4 5 3 1 2
rank( manyNumbersWithNA[1:5] )
[1] 4 5 3 1 2
sort( mixedLetters )
 [1] "I" "j" "L" "q" "Q" "R" "s" "t" "u" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 8.5 3.0 6.0 8.5 8.5 2.0 1.0 4.5 8.5 4.5
rank( manyDuplicates, ties.method = "min" )
 [1] 7 3 6 7 7 2 1 4 7 4
rank( manyDuplicates, ties.method = "random" )
 [1]  7  3  6  9 10  2  1  4  8  5

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -0.8659098 -0.4805927 -1.3888874  0.6737903
[10]  1.3004349 -1.3141006 -0.4099081 -2.0417147 -0.4467982  2.0714691
round( v, 0 )
 [1] -1  0  0  0  1 -1  0 -1  1  1 -1  0 -2  0  2
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.9 -0.5 -1.4  0.7  1.3 -1.3 -0.4 -2.0 -0.4  2.1
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.87 -0.48 -1.39  0.67  1.30 -1.31 -0.41 -2.04 -0.45  2.07
floor( v )
 [1] -1 -1  0  0  1 -1 -1 -2  0  1 -2 -1 -3 -1  2
ceiling( v )
 [1] -1  0  0  1  1  0  0 -1  1  2 -1  0 -2  0  3

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC